Development and External Evaluation of Predictions Models for Mortality of COVID-19 Patients using Machine Learning Method (preprint)

Background To develop and evaluate the prognostic machine-learning model for mortality in patients with coronavirus disease 2019 (COVID-19).Methods Clinical data of confirmed COVID-19 were retrospectively collected from Wuhan between 18th January and 29th March 2020. Gradient Boosting Decision Tree (GBDT), logistic regression (LR) model, and simplified LR with selected 5 features (LR-5) model were built to predict the mortality of COVID-19. 5-fold area under curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated and compared between models.Results A total of 2,924 patients were included in the final analysis, 257(8.8%) of whom died during hospitalization and 2,667 (91.2%) survived. There were 21(0.7%) mild cases, 2,051(70.1%) moderate case, 779(26.6%) severe cases, and 73(2.5%) critically severe cases of COVID-19 on admission. The overall 5-fold AUC was observed highest in GBDT model (0.941), followed by LR (0.928) and LR-5 (0.913). The diagnostic accuracy were 0.889 in GBDT, 0.868 in LR and 0.887 in LR-5. GBDT model also showed the highest sensitivity (0.899) and speciality (0.889). The NPV of all three models exceeded 97%, while the PPV were relatively low in all models, 0.381 for LR, 0.402 for LR-5 and 0.432 for GBDT. In subgroups analysis with severe cases only, GBDT model also performed the best with a accuracy of 0.799 and 5-fold AUC (0.918).Conclusion The finding revealed that mortality prediction performance of the GBDT was superior to the LR models in confirmed cases of COVID-19, regardless of disease severity.

Safety, Tolerability and Immunogenicity of a Recombinant Adenovirus Type 5 Vectored COVID-19 Vaccine in Healthy Adults in China: Preliminary Report of a First-In Human Single-Center, Open-Label, Dose-Escalating Clinical Trial (preprint)

Background: We aimed to assess the safety, tolerability and immunogenicity of a recombinant adenovirus type 5 (Ad5) vectored COVID-19 vaccine expressing the spike glycoprotein of a SARS-Cov-2 strain. This is the first-in-human study of a candidate vaccine against COVID-19.Methods: We conducted a single-center, open-label, dose-escalating clinical trial of Ad5 vectored COVID-19 vaccine. Healthy adults aged between 18-60 years were sequentially enrolled and allocated to receive a single intramuscular injection in one of three dose groups: 5 × 10^10, 1×10^11, and 1·5×10^11 viral particles. Safety was assessed over the next 28 days. Specific antibodies were measured on enzyme-linked immunosorbent assay (ELISA), and the neutralizing antibody responses induced by vaccination were detected by using SARS-CoV-2 virus neutralization and pseudovirus neutralization tests. T-cell responses were accessed by enzyme-linked immunospot (ELISpot) and flow-cytometry assays. Results: A total of 108 participants were recruited and received low dose, middle dose, or high dose vaccine, with 36 in each dose group. 30(83·3%), 30(83·3%), and 27(75·0%) recipients in the low dose, middle dose, and high dose groups reported at least one adverse reaction within the first 7 days after the vaccination. The most common injection-site adverse reaction was pain, the most commonly reported systematic adverse reactions were fever, fatigue, headache, and muscle pain. A majority of the adverse reactions that were reported in all dose groups were mild or moderate in severity. No serious adverse event was noted within 28 days post-vaccination. Both ELISA antibodies and neutralizing antibodies increased significantly at day 14, and peaked 28 days post-vaccination. Specific T cell response peaked at day 14 post-vaccination.Conclusions: The Ad5 vectored COVID-19 vaccine is tolerable and immunogenic. Humoral responses against SARS-CoV-2 peaked at day 28 post-vaccination in health adults, and rapid specific T cell responses were noted since day 14.Trial Registration: The study is registered with ClinicalTrials.gov, number NCT04313127. Funding Statement: National Key R&D Program of China (2020YFC10841400), National Science and Technology Major Project (2016ZX10004001, 2018ZX09201005), and CanSino Biotechnology Inc.Declaration of Interests: Mr. Gou report being employees of Tianjin CanSino Biotechnology Inc, No other potential conflict of interest relevant to this article was reported.Ethics Approval Statement: The protocol and informed consent were approved by the Institutional Review Board of the Jiangsu Provincial Center of Disease Control and Prevention. Written informed consents from all participants were obtained before screening. This study was undertaken by Jiangsu Provincial Center of Disease Control and Prevention, Hubei Provincial Center for Disease Control and Prevention and Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology in accordance with the Declaration of Helsinki and Good Clinical Practice.

COVID-19 in Wuhan: Sociodemographic Characteristics and Hospital Support Measures Associated with the Immediate Psychological Impact on Healthcare Workers (preprint)

Background: The outbreak of COVID-19 has laid unprecedented threats and challenges to health workers (HWs) in Wuhan, China. We aimed to assess the sociodemographic characteristics and hospital support measures associated with the immediate psychological impact on HWs at Tongji Hospital in Wuhan during COVID-19 outbreak. Methods: We conducted a single-center, cross-sectional survey of HWs via online questionnaires between February 8th and 10th, 2020. We evaluated stress, depression and anxiety by IES-R, PHQ-9, and GAD-7, respectively. We also designed a questionnaire to assess the perceptions of threat of COVID-19, and the effect of the hospital’s support measures. Multivariate logistic regression was used to identify predictors of acute stress, depression, and anxiety. Findings: We received 5062 completed questionnaires (response rate, 77.1%). 29.8%, 13.5% and 4.1% HWs reported stress, depression and anxiety symptoms. Women (odds ratio[OR], 1.31; 95%CI, 0.47-0.97; p=0.032), years of working >10 years (OR, 2.02; 95%CI, 1.47-2.79; p<0.001), concomitant chronic diseases (OR, 1.51; 95%CI, 1.27-1.80; p<0.001), history of mental disorders (OR, 3.27; 95%CI, 1.77-6.05; p<0.001), and family members or relatives confirmed or suspected (OR, 1.23; 95%CI, 1.02-1.48; p=0.03) were risk factors for stress, whereas hospital-based and department-based care (OR, 0.76; 95%CI, 0.60-0.97; p=0.024) and full coverage of all departments for avoiding nosocomial infection(OR, 0.69; 95%CI, 0.53-0.89; p=0.004) were protective factors. Interpretation: Women and those who have more than 10 years of working, concomitant chronic diseases, history of mental disorders, and family members or relatives confirmed or suspected are susceptible to stress, depression and anxiety among HWs during the epidemic. The hospital’s support measures could be helpful.Funding Statement: Supported by the grants 2017YFC1310000 from the National Key Research and Development Program of the Ministry of Science and Technology of China and 2018KFYXMPT015 from Research and Development Office of Huazhong University of Science and Technology. Declaration of Interests: The authors declare that they have no competing interests.Ethics Approval Statement: The study was approved by the institutional ethics board of Tongji Hospital, Tongji Medical College of Huazhong University of Science and Technology (ID: TJ-C20200129). The data analyses were done on unidentified datasets.

The corticosteroid treatment and response of patients with COVID-19 in Hubei, China: a retrospective, cohort study (preprint)

Background Since December 2019, COVID-19 has emerged in Wuhan, China and spread globally. As of now, there is still no explicit therapeutic regimen and the use of corticosteroid is also controversial. We aimed to explore the effectiveness of corticosteroid and provide evidence for the rational use of corticosteroid in different patients with COVID-19.Methods In this multi-centered, retrospective study, we extracted the clinical data of 649 cases with COVID-19 with definite outcome (discharged or dead) from 14 hospitals in Hubei province, and evaluated the clinical characteristics, treatment regimens, and their association with outcomes.Results Ninety-five of 649 patients had died. Older male patients with comorbidities had an increased risk of death and more obvious abnormalities in clinical indicators. Corticosteroid, γ-globulin treatment and invasive ventilation were more frequently used in non-survivors. Survivors with corticosteroid treatment had a prolonged hospitalization. The median time duration for temperature restore for non-survivors after corticosteroid treatment was longer than that of both survivors. The lymphocyte count on admission was lower in the patients treated with corticosteroids compared to those without corticosteroid treatment. Lymphocyte count recovered significantly after corticosteroid treatment in survivors, but not in non-survivors.Conclusions The responses to corticosteroid treatment were different in COVID-19 patients with different outcomes. The surviving patients with relatively lower lymphocyte count were more likely to be given corticosteroids. For non-survivors, the lymphocyte count was too low and the effect of corticosteroids was poor. Survivors under corticosteroid treatment had a prolonged hospitalization, but had a recovery of lymphocytes. The recovery of lymphocyte count and temperature after corticosteroid treatment may be used as predictors of prognosis of patients with COVID-19.

COVID-19 in Wuhan: Immediate Psychological Impact on 5062 Health Workers (preprint)

BACKGROUND: The outbreak of COVID-19 has laid unprecedented psychological stress on health workers (HWs). We aimed to assess the immediate psychological impact on HWs at Tongji Hospital in Wuhan, China. METHODS: We conducted a single-center, cross-sectional survey of HWs via online questionnaires between February 8th and 10th, 2020. We evaluated stress, depression and anxiety by Impact of Event Scale-Revised (IES-R), Patient Health Questionnaire-9 (PHQ-9), and Generalized Anxiety Disorder 7-item (GAD-7), respectively. We also designed a questionnaire to assess the effect of psychological protective measures taken by Tongji Hospital. Multivariate logistic regression was used to identify predictors of acute stress, depression, and anxiety. RESULTS: We received 5062 completed questionnaires (response rate, 77.1 percent). 1509 (29.8 percent), 681 (13.5 percent) and 1218 (24.1 percent) HWs reported stress, depression and anxiety symptoms. Women (hazard ratio[HR], 1.31; P=0.032), years of working> 10 years (HR, 2.02; P<0.001), concomitant chronic diseases (HR, 1.51; P<0.001), history of mental disorders (HR, 3.27; P<0.001), and family members or relatives confirmed or suspected (HR, 1.23; P=0.030) were risk factors for stress, whereas care provided by hospital and department administrators(odds ratio [OR], 0.76; P=0.024) and full coverage of all departments with protective measures (OR, 0.69; P=0.004) were protective factors. CONCLUSIONS: Women and those who have more than 10 years of working, concomitant chronic diseases, history of mental disorders, and family members or relatives confirmed or suspected are susceptible to stress, depression and anxiety among HWs during the COVID-19 pandemic. Psychological protective measures implemented by the hospital could be helpful.